A Computer Vision Approach to Radial Velocity Extraction for Exoplanet Detection

Abstract

For many decades, cross-correlating spectral data with a template mask has been the standard approach to radial velocity (RV) extraction for exoplanet detection. In this proof-of-concept paper, we present a novel approach that utilizes computer vision (CV) techniques to analyze stellar spectra and accurately extract RVs. We tested our method on four real stellar data sets and found that it yields results comparable to an industry-standard, chunk-by-chunk (CBC) method in both time and frequency domains, with remarkable robustness and speed. This CV technique could enable the detection of exoplanets that are currently difficult to detect due to stellar variability and activity.